A guide for implementing tridiagonal solvers on GPUs

DOI10.1007/978-3-319-06548-9_2MaRDI QIDQ5261391zbMATH OpenOpenAlexFDO

Authors Li-Wen Chang, Wen-Mei W. Hwu

Publication date 3 July 2015

Published in Numerical Computations with GPUs (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-06548-9_2

zbMATH Keywords

algorithmoptimization strategiestridiagonal solver

Mathematics Subject Classification ID

Direct numerical methods for linear systems and matrix inversion (65F05) Computational methods for sparse matrices (65F50)

Recommendations

• Manycore algorithms for batch scalar and block tridiagonal solvers
• An efficient GPU implementation of cyclic reduction solver for high-order compressible viscous flow simulations
• A fast dense triangular solve in CUDA
• Redesigning triangular dense matrix computations on GPUs
• Speedup of tridiagonal system solvers

Cited in

(8)

• Redesigning triangular dense matrix computations on GPUs
• Alternating direction implicit time integrations for finite difference acoustic wave propagation: parallelization and convergence
• A fast dense triangular solve in CUDA
• Solving Large Problem Sizes of Index-Digit Algorithms on GPU: FFT and Tridiagonal System Solvers
• Tree partitioning reduction: a new parallel partition method for solving tridiagonal systems
• A flexible CUDA LU-based solver for small, batched linear systems
• Manycore algorithms for batch scalar and block tridiagonal solvers
• \texttt{PittPack}: an open-source Poisson's equation solver for extreme-scale computing with accelerators

Describes a project that uses

Uses Software

• CUDA
• CUSPARSE

This page was built for publication: A guide for implementing tridiagonal solvers on GPUs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5261391)